AI-Assisted Statistics for Data Scientists, 3rd Edition
by Peter Bruce, Andrew Bruce, Peter Gedeck
Chapter 8. Neural Networks
Neural networks are complex and flexible predictive models that take input and, via a complex set of paths and intermediate calculations, produce output. This chapter introduces the basic structure and functioning of neural networks. Later chapters cover the larger and more complex networks that are now used (Chapter 9), as well as the models that are used in generative AI (Chapter 10).
The Basic Structure of a Neural Net
Neural nets drew their inspiration from abstract models of the human brain in which interconnected neurons process information. The basic structure of a neural network algorithm was established by F. Rosenblatt in his paper “The Perceptron: A Probabilistic Model For Information Storage And Organization In The Brain” (1958). He posited an input layer, a hidden layer, and an output layer. Neural nets saw early application in the late 1990s but did not take off until the early 2000s with the development of more complex networks and the growing power of computers.
The original standard neural ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access